GitGyun/visual_token_matching

[ICLR'23 Oral] Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching

37
/ 100
Emerging

This project helps researchers and engineers quickly train computer vision models for complex tasks like depth estimation or semantic segmentation, even with very little data. You provide a small set of labeled images, and the system outputs a trained model capable of performing detailed pixel-level predictions on new, unseen images. It's ideal for those working in areas like robotics, autonomous vehicles, or medical imaging who need to adapt models to specific environments or datasets efficiently.

255 stars. No commits in the last 6 months.

Use this if you need to develop accurate image analysis models for tasks like identifying objects, edges, or depth, but have limited labeled data for training.

Not ideal if your main goal is simple image classification (e.g., categorizing an entire image) rather than detailed pixel-level predictions, or if you have abundant labeled data.

computer-vision image-segmentation depth-estimation robotics-vision medical-imaging-analysis
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 11 / 25

How are scores calculated?

Stars

255

Forks

13

Language

Python

License

MIT

Last pushed

Oct 13, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/GitGyun/visual_token_matching"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.